List your company

Research

Benchmarks

Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.

309,131 benchmarksPage 1840 of 12,366

Benchmarks

TaskDatasetDomainTrendResultsLast update
Persona DiscoveryQwen3-80B Large Targetllm chat instruction18Apr 28, 2026
Persona DiscoveryLlama-3.1-70B Large Targetllm chat instruction18Apr 28, 2026
Persona DiscoveryQwen3-30B Large Targetllm chat instruction18Apr 28, 2026
Persona DiscoveryGemini Flash (Small Target) 2.5llm chat instruction18Apr 28, 2026
Persona DiscoveryLlama 8B Small Target 3.1llm chat instruction18Apr 28, 2026
Persona DiscoveryQwen3-1.7B Small Targetllm chat instruction18Apr 28, 2026
Question AnsweringARC Challenge 25-shotnlp18Apr 28, 2026
Inductive ReasoningDEER (test)nlp18Apr 28, 2026
Deductive ReasoningJustLogic (test)nlp18Apr 28, 2026
Out-of-Distribution DetectionCIFAR-100 (ID) vs SVHN (OOD) 1.0 (test)computer visiontabular time series18Apr 28, 2026
Anomaly SegmentationSemanticPOSS OoDcomputer visionbio medical18Apr 28, 2026
Anomaly SegmentationSTU (val)computer visionbio medical18Jun 2, 2026
ClassificationTCGA-LUCAcomputer visionnlp+318Apr 28, 2026
Multi-agent executionWarehouse map 100 agentsagents tool userobotics embodied ai18Apr 28, 2026
Logistic RegressionSynthetic d=20 (test)tabular time series18Apr 28, 2026
Linear RegressionSynthetic d=20 (test)tabular time series18Apr 28, 2026
Logistic RegressionSynthetic d=40 1.0 (test)tabular time series18Apr 28, 2026
Linear RegressionSynthetic d=40 1.0 (test)tabular time series18Apr 28, 2026
StagingHigh Dimensional Synthetic Data B = 100 biomarkers v1tabular time series18Apr 28, 2026
SequencingHigh Dimensional Synthetic Data B = 100 biomarkers v1bio medical18Apr 28, 2026
Multi-class digit classificationMNIST (train)computer vision18Apr 28, 2026
Text-to-Image RetrievalMedical Image-Report Retrievalmultimodalretrieval search rag18Apr 28, 2026
Image-to-Text RetrievalMedical Image-Report Retrievalmultimodalretrieval search rag18Apr 28, 2026
Trajectory PredictionOPV2V Vehicle 1 (val)robotics embodied aitabular time series18Apr 28, 2026
Iris IdentificationImmerIris Left eyecomputer vision18Apr 28, 2026